adrianSauer/wav2vec2-wer

Common Voice 16

This model is a fine-tuned version of glob-asr/wav2vec2-large-xls-r-300m-guarani-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3513
• Wer: 49.7668

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4171	1.0152	100	0.3798	55.2965
0.3376	2.0305	200	0.3628	53.8974
0.294	3.0457	300	0.3528	52.4983
0.2632	4.0609	400	0.3484	49.7668
0.2459	5.0761	500	0.3513	49.7668

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1